Dataset Information

Analysis of responder-based endpoints: improving power through utilising continuous components.

ABSTRACT:

Background

Clinical trials and other studies commonly assess the effectiveness of an intervention through the use of responder-based endpoints. These classify patients based on whether they meet a number of criteria which often involve continuous variables categorised as being above or below a threshold. The proportion of patients who are responders is estimated and, where relevant, compared between groups. An alternative method called the augmented binary method keeps the definition of the endpoint the same but utilises information contained within the continuous component to increase the power considerably (equivalent to increasing the sample size by >?30%). In this article we summarise the method and investigate the variety of clinical conditions that use endpoints to which it could be applied.

Methods

We reviewed a database of core outcome sets (COSs) that covered physiological and mortality trial endpoints recommended for collection in clinical trials of different disorders. We identified responder-based endpoints where the augmented binary method would be useful for increasing power.

Results

Out of the 287 COSs reviewed, we identified 67 new clinical areas where endpoints were used that would be more efficiently analysed using the augmented binary method. Clinical areas that had particularly high numbers were rheumatology (11 clinical disorders identified), non-solid tumour oncology (10 identified), neurology (9 identified) and cardiovascular (8 identified).

Conclusions

The augmented binary method can potentially provide large benefits in a vast array of clinical areas. Further methodological development is needed to account for some types of endpoints.

SUBMITTER: Wason J

PROVIDER: S-EPMC7249409 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Analysis of responder-based endpoints: improving power through utilising continuous components.

Wason James J McMenamin Martina M Dodd Susanna S

Trials 20200525 1

<h4>Background</h4>Clinical trials and other studies commonly assess the effectiveness of an intervention through the use of responder-based endpoints. These classify patients based on whether they meet a number of criteria which often involve continuous variables categorised as being above or below a threshold. The proportion of patients who are responders is estimated and, where relevant, compared between groups. An alternative method called the augmented binary method keeps the definition of ...[more]

PMID: 32450909

Similar Datasets

Project description:BackgroundComposite endpoints are recommended in rare diseases to increase power and/or to sufficiently capture complexity. Often, they are in the form of responder indices which contain a mixture of continuous and binary components. Analyses of these outcomes typically treat them as binary, thus only using the dichotomisations of continuous components. The augmented binary method offers a more efficient alternative and is therefore especially useful for rare diseases. Previous work has indicated the method may have poorer statistical properties when the sample size is small. Here we investigate small sample properties and implement small sample corrections.MethodsWe re-sample from a previous trial with sample sizes varying from 30 to 80. We apply the standard binary and augmented binary methods and determine the power, type I error rate, coverage and average confidence interval width for each of the estimators. We implement Firth's adjustment for the binary component models and a small sample variance correction for the generalized estimating equations, applying the small sample adjusted methods to each sub-sample as before for comparison.ResultsFor the log-odds treatment effect the power of the augmented binary method is 20-55% compared to 12-20% for the standard binary method. Both methods have approximately nominal type I error rates. The difference in response probabilities exhibit similar power but both unadjusted methods demonstrate type I error rates of 6-8%. The small sample corrected methods have approximately nominal type I error rates. On both scales, the reduction in average confidence interval width when using the adjusted augmented binary method is 17-18%. This is equivalent to requiring a 32% smaller sample size to achieve the same statistical power.ConclusionsThe augmented binary method with small sample corrections provides a substantial improvement for rare disease trials using composite endpoints. We recommend the use of the method for the primary analysis in relevant rare disease trials. We emphasise that the method should be used alongside other efforts in improving the quality of evidence generated from rare disease trials rather than replace them.

Project description:PurposeThere have been concerns that short-term clinical trials for evaluating new treatments in glaucoma would require prohibitively large sample sizes when using visual field endpoints, given that glaucoma is often a slowly progressive disease. This study sought to determine the required sample size for such trials using event-based analyses, and whether it can be reduced using trend-based analyses.DesignLongitudinal, observational study.Participants321 eyes of 240 glaucoma participants followed under routine clinical care using 242 visual field for an average of 10 years.MethodsSample size requirements were derived using computer simulations that reconstructed "real-world" visual fields by combining estimates of point-wise variability according to different threshold levels and rates of change obtained from the clinical glaucoma cohort. A clinical trial lasting 2 years with testing every 3 months was simulated, assuming that the new treatment halted visual field change in various percentages of participants (or "responders"). Treatment efficacy was evaluated by: (a) Difference in incidence of point-wise event-based progression (similar to the commercially available Guided Progression Analysis), and (b) Difference in rate of visual field mean deviation (MD) change between groups using linear mixed models (LMMs).Main outcome measuresSample size to detect a statistically significance difference between groups.ResultsBetween-group trend-based analyses using LMMs reduced sample size requirements by 85-90% across the range of new treatment effects when compared to the conventional point-wise event-based analysis. To detect the effect of a new treatment that halted progression in 30% of the participants under routine clinical care (equal to a 30% reduction in average rate of MD change) with 90% power, for example, 1924 participants would be required per group using event-based analysis, but only 277 participants per group if LMMs were used.ConclusionsThe feasibility of future glaucoma clinical trials can be substantially improved by evaluating differences in the rate of visual field change between groups.

Dataset Information

Analysis of responder-based endpoints: improving power through utilising continuous components.

Background

Methods

Results

Conclusions

Publications

Analysis of responder-based endpoints: improving power through utilising continuous components.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets